scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-08-28 04:24:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
claude-skills/productivity/weekly-review
History
Claude 7405298b4b
fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 
- #954: strip non-spec source/attribution keys from all 39 plugin.json
  manifests so Claude Code's validator accepts them; metadata preserved in
  new .claude-plugin/authoring-notes.json sidecars; check_plugin_json.py now
  hard-fails manifests carrying those keys and sanity-checks the sidecar;
  CLAUDE.md ClawHub schema section updated to the new rule.
- #949: move the c-level-agents plugin out of c-level-advisor/ to a
  top-level directory so the two marketplace sources no longer overlap;
  updated marketplace.json source, homepage, descriptions, all
  cross-references, docs, harness manifest, mirror-tree symlinks/indexes,
  and rebased the moved files' relative links; domain counters trued up
  (18 -> 19 domains).
- #933: replace dead links to the gitignored maintainer-local megaprompts/
  tree with annotated plain-text references (44 files: SKILL.md, READMEs,
  agents, commands).
- #931: DynamoDB on-demand pricing updated to post-Nov-2024 rates
  ($0.625/M writes, $0.125/M strongly consistent reads).
- #969: skill_security_auditor.py and the three dossier scripts reconfigure
  stdout/stderr to UTF-8 (errors=replace) so legacy Windows codepages no
  longer crash at print time; PYTHONUTF8=1 documented.
- #968: Windows Notes section in INSTALLATION.md + README pointer for the
  core.symlinks mirror-tree checkout caveat.
- #924/#885 residuals: hook commands quote "${CLAUDE_PLUGIN_ROOT}" paths in
  all plugin hooks.json/settings.json (space-safe roots); removed the stale
  pre-rename status/review mirror symlinks and index entries left over from
  the memory-status/memory-review rename.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Qgc6RYXWJPr5oW9DHU7zR4
2026-08-21 05:47:37 +00:00
..
.claude-plugin fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00
agents feat(productivity): add weekly-review plugin — GTD weekly-review loop 2026-07-17 06:10:42 +00:00
commands feat(productivity): add weekly-review plugin — GTD weekly-review loop 2026-07-17 06:10:42 +00:00
skills/weekly-review feat(productivity): add weekly-review plugin — GTD weekly-review loop 2026-07-17 06:10:42 +00:00
README.md feat(productivity): add weekly-review plugin — GTD weekly-review loop 2026-07-17 06:10:42 +00:00

README.md

weekly-review — GTD Weekly Review Loop → Trusted System

Close every open loop once a week. David Allen called the weekly review the "critical success factor" of the whole method — the system is only trustworthy if it gets reviewed.

/cs:weekly-review walks the three-phase GTD ritual — GET CLEAR → GET CURRENT → GET CREATIVE — and refuses to call the review COMPLETE while any of the five mandatory GET CURRENT steps is unaccounted for. Deterministic scripts do the inventory and the gating; you (and Claude) do the thinking.

The three phases

Phase What it does Steps
GET CLEAR Ground zero: nothing loose, nothing unprocessed Collect loose inputs · process inboxes to zero · empty your head
GET CURRENT The mandatory core — the system matches reality again Next-action lists · previous calendar · upcoming calendar · waiting-for list · project lists
GET CREATIVE Lift your eyes off the runway Someday/maybe review · capture new ideas

Skipping a GET CURRENT step without a stated reason always forces an INCOMPLETE verdict. That gate is the whole point: a weekly review that skims the core is a guilt ritual, not a review.

Quick start

# 1. Inventory the open loops in a workspace (checkboxes, TODO/FIXME, stale files)
python skills/weekly-review/scripts/open_loop_scanner.py --dir ~/notes --stale-days 14

# 2. Walk the checklist, then gate it — names every missing step
python skills/weekly-review/scripts/weekly_review_gate.py --list
python skills/weekly-review/scripts/weekly_review_gate.py --done "1,2,3,4,5,6,7,8" --skip "9:no someday list yet"

# 3. Audit the commitment portfolio — STALLED / NO-NEXT-ACTION / SOMEDAY-CANDIDATE + health score
python skills/weekly-review/scripts/commitment_auditor.py --input commitments.json

Or just say "run my weekly review" or run /cs:weekly-review.

What's in the box

  • Skill: skills/weekly-review/SKILL.md
  • Agent: agents/cs-weekly-review.md
  • Command: commands/cs-weekly-review.md — /cs:weekly-review
  • 3 stdlib scripts: open_loop_scanner.py, weekly_review_gate.py, commitment_auditor.py
  • 3 references (5-7 sources each): the GTD weekly-review canon, the psychology of open loops (Zeigarnik, attention residue, plan-making), and sustainable review-cadence design
  • 2 assets: fillable weekly-review checklist + a full worked example

Not the same as

  • productivity/reflect — reflects on one conversation or piece of work, once. The weekly review is a recurring cadence over your whole system.
  • productivity/capture — the intake funnel (brain dump → actions). Capture feeds the system; the weekly review is how the system stays trusted.
  • Sprint retrospectives (project-management) — a team ceremony about a shared iteration. This is a personal trusted-system audit; no team required.

License

MIT.